Below are descriptive and correlational statistics with data from to the International Civic and Citizenship Education Study (ICCS) 2009 and 2016, in which six (Chile, Mexico, Colombia, Paraguay, Guatemala, and the Dominican Republic) and five (Chile, Mexico, Colombia, Peru, and the Dominican Republic) Latin American countries participated, respectively. The following sections are presented: change in support for dictatorship, support for Dictatorship on civic knowledge and support for Dictatorship on institutional trust
ICCS 2009: Chile, Mexico, Colombia, Paraguay, Guatemala, and the Dominican Republic
ICCS 2016: Chile, Mexico, Colombia, Peru, and the Dominican Republic
#Data frames with all variables
#2009
dict09 = iccs09 %>%
mutate(time = 2009) %>%
mutate(country = COUNTRY) %>%
mutate(idcountry = IDCNTRY) %>%
mutate(idschool = IDSCHOOL) %>%
mutate(idstudent = IDSTUD) %>%
mutate(idstudent = (time*1000000000000 + idcountry*100000000 + idstudent)) %>% #NEW IDSTUDENT
mutate(dict_safety = 5-LS2P03D) %>% #DICTATORSHIPS ARE JUSTIFIED WHEN THEY BRING ORDER AND SAFETY
mutate(dict_benefits = 5-LS2P03E) %>% #DICTATORSHIPS ARE JUSTIFIED WHEN THEY BRING ECONOMIC BENEFITS
mutate(dict = (dict_safety + dict_benefits)/2) %>% #MEAN DIC
mutate(pv1civ = PV1CIV) %>%
mutate(pv2civ = PV2CIV) %>%
mutate(pv3civ = PV3CIV) %>%
mutate(pv4civ = PV4CIV) %>%
mutate(pv5civ = PV5CIV) %>%
mutate(civic_knowledge = (pv1civ + pv2civ + pv3civ + pv4civ + pv5civ)/5) %>% #MEAN CIVIC KNOWLEDGE
mutate(s_intrust = INTRUST) %>% #TRUST IN CIVIC INSTITUTIONS
mutate(s_opdisc = OPDISC) %>% #OPENNESS IN CLASS DISCUSSION
mutate(s_hisced = HISCED) %>% #HIGHEST PARENTAL EDUCATIONAL LEVEL
mutate(univ = ifelse(s_hisced>3, 1, 0)) %>% #UNIVERSITARY PARENTS
mutate(s_hisei = HISEI) %>% #PARENT'S HIGHEST OCCUPATIONAL STATUS
mutate(s_homelit = HOMELIT) %>% #HOME LITERACY
mutate(s_gender = SGENDER) %>% #GENDER OF STUDENT
mutate(s_citcon = CITCON) %>% #CONVENTIONAL CITIZENSHIP
mutate(s_citsoc = CITSOC) %>% #SOCIAL MOVEMENT REL. CITIZENSHIP
mutate(s_citeff = CITEFF) %>% #CITIZENSHIP SELF-EFFICACY
mutate(s_cntatt = ATTCNT) %>% #ATTITUDES TOWARDS OWN COUNTRY
mutate(s_geneql = GENEQL) %>% #ATTITUDES TOWARDS GENDER EQUALITY
mutate(s_ethrght = ETHRGHT) %>% #EQUAL RIGHTS FOR ALL ETHNIC GROUPS
mutate(l_attviol = ATTVIOL) %>% #ATTITUDES: USE OF VIOLENCE
mutate(l_attdiv = ATTDIFF) %>% #ATTITUDES: NEIGHBOURHOOD DIVERSITY
mutate(l_autgov = AUTGOV) %>% #AUTHORITARIANISM IN GOVERNMENT
mutate(l_attcorr = ATTCORR) %>% #CORRUPT PRACTICES IN GOVERNMENT
mutate(l_dislaw = DISLAW) %>% #ATTITUDES: DISOBEYING THE LAW
mutate(l_empclas = EMPATH) %>% #EMPATHY TOWARDS CLASSMATES
mutate(s_poldisc = POLDISC) %>% #DISCUSSION OF POL. AND SOC. ISSUES
#TRUST
mutate(nac_gob = IS2P27A) %>% #TRUST INSTITUTIONS-NATIONAL GOVERNMENT
mutate(local_gob = IS2P27B) %>% #TRUST INSTITUTIONS-LOCAL GOVERNMENT
mutate(courts = IS2P27C) %>% #TRUST INSTITUTIONS-COURTS
mutate(police = IS2P27D) %>% #TRUST INSTITUTIONS-POLICE
mutate(pol_parties = IS2P27E) %>% #TRUST INSTITUTIONS-POLITICAL PARTIES
mutate(parliament = IS2P27F) %>% #TRUST INSTITUTIONS-PARLIAMENT
mutate(media = IS2P27G) %>% #TRUST INSTITUTIONS-MEDIA
mutate(ffaa = IS2P27H) %>% #TRUST INSTITUTIONS-FFAA
mutate(school = IS2P27I) %>% #TRUST INSTITUTIONS-SCHOOL
mutate(unit_nations = IS2P27J) %>% #TRUST INSTITUTIONS-UNITED NATIONS
mutate(people = IS2P27K) %>% #TRUST INSTITUTIONS-PEOPLE
#WEITHINGS
mutate(totwgts = TOTWGTS) %>% #FINAL STUDENT WEIGHT
mutate(wgtfac1 = WGTFAC1) %>% #SCHOOL BASE WEIGHT
mutate(wgtadj1s = WGTADJ1S) %>% #SCHOOL WEIGHT ADJUSTMENT-STUDENT STUDY
mutate(wgtfac2s = WGTFAC2S) %>% #CLASS WEIGHT FACTOR
mutate(wgtadj2s = WGTADJ2S) %>% #CLASS WEIGHT ADJUSTMENT
mutate(wgtadj3s = WGTADJ3S) %>% #STUDENT WEIGHT ADJUSTMENT
mutate(jkzones = JKZONES) %>% #JACKKNIFE ZONE - STUDENT STUDY
mutate(jkreps = JKREPS) %>% #JACKKNIFE REPLICATE CODE
select(411:463)
#2016
dict16 = iccs16 %>%
mutate(time = 2016) %>%
mutate(country = COUNTRY) %>%
mutate(idcountry = IDCNTRY) %>%
mutate(idschool = IDSCHOOL) %>%
mutate(idstudent = IDSTUD) %>%
mutate(idstudent = (time*100000000000 + idcountry*100000000 + idstudent)) %>% #NEW IDSTUDENT
mutate(dict_safety = 5-LS3G02D) %>% #DICTATORSHIPS ARE JUSTIFIED WHEN THEY BRING ORDER AND SAFETY
mutate(dict_benefits = 5-LS3G02E) %>% #DICTATORSHIPS ARE JUSTIFIED WHEN THEY BRING ECONOMIC BENEFITS
mutate(dict = (dict_safety + dict_benefits)/2) %>% #MEAN DIC
mutate(pv1civ = PV1CIV) %>%
mutate(pv2civ = PV2CIV) %>%
mutate(pv3civ = PV3CIV) %>%
mutate(pv4civ = PV4CIV) %>%
mutate(pv5civ = PV5CIV) %>%
mutate(civic_knowledge = (pv1civ + pv2civ + pv3civ + pv4civ + pv5civ)/5) %>% #MEAN CIVIC KNOWLEDGE
mutate(s_intrust = S_INTRUST) %>% #TRUST IN CIVIC INSTITUTIONS
mutate(s_opdisc = S_OPDISC) %>% #OPENNESS IN CLASS DISCUSSION
mutate(s_hisced = S_HISCED) %>% #HIGHEST PARENTAL EDUCATIONAL LEVEL
mutate(univ = ifelse(s_hisced>3, 1, 0)) %>% #UNIVERSITARY PARENTS
mutate(s_hisei = S_HISEI) %>% #PARENT'S HIGHEST OCCUPATIONAL STATUS
mutate(s_homelit = S_HOMLIT) %>% #HOME LITERACY
mutate(s_gender = S_GENDER) %>% #GENDER OF STUDENT
mutate(s_citcon = S_CITCON) %>% #CONVENTIONAL CITIZENSHIP
mutate(s_citsoc = S_CITSOC) %>% #SOCIAL MOVEMENT REL. CITIZENSHIP
mutate(s_citeff = S_CITEFF) %>% #CITIZENSHIP SELF-EFFICACY
mutate(s_cntatt = S_CNTATT) %>% #ATTITUDES TOWARDS OWN COUNTRY
mutate(s_geneql = S_GENEQL) %>% #ATTITUDES TOWARDS GENDER EQUALITY
mutate(s_ethrght = S_ETHRGHT) %>% #EQUAL RIGHTS FOR ALL ETHNIC GROUPS
mutate(l_attviol = L_ATTVIOL) %>% #ATTITUDES: USE OF VIOLENCE
mutate(l_attdiv = L_ATTDIV) %>% #ATTITUDES: NEIGHBOURHOOD DIVERSITY
mutate(l_autgov = L_AUTGOV) %>% #AUTHORITARIANISM IN GOVERNMENT
mutate(l_attcorr = L_ATTCORR) %>% #CORRUPT PRACTICES IN GOVERNMENT
mutate(l_dislaw = L_DISLAW) %>% #ATTITUDES: DISOBEYING THE LAW
mutate(l_empclas = L_EMPCLAS) %>% #EMPATHY TOWARDS CLASSMATES
mutate(s_poldisc = S_POLDISC) %>% #DISCUSSION OF POL. AND SOC. ISSUES
#TRUST
mutate(nac_gob = IS3G26A) %>% #TRUST INSTITUTIONS-NATIONAL GOVERNMENT
mutate(local_gob = IS3G26B) %>% #TRUST INSTITUTIONS-LOCAL GOVERNMENT
mutate(courts = IS3G26C) %>% #TRUST INSTITUTIONS-COURTS
mutate(police = IS3G26D) %>% #TRUST INSTITUTIONS-POLICE
mutate(pol_parties = IS3G26E) %>% #TRUST INSTITUTIONS-POLITICAL PARTIES
mutate(parliament = IS3G26F) %>% #TRUST INSTITUTIONS-PARLIAMENT
mutate(media = IS3G26G) %>% #TRUST INSTITUTIONS-MEDIA
mutate(ffaa = IS3G26I) %>% #TRUST INSTITUTIONS-FFAA
mutate(school = IS3G26J) %>% #TRUST INSTITUTIONS-SCHOOL
mutate(unit_nations = IS3G26K) %>% #TRUST INSTITUTIONS-UNITED NATIONS
mutate(people = IS3G26L) %>% #TRUST INSTITUTIONS-PEOPLE
#WEITHINGS
mutate(totwgts = TOTWGTS) %>% #FINAL STUDENT WEIGHT
mutate(wgtfac1 = WGTFAC1) %>% #SCHOOL BASE WEIGHT
mutate(wgtadj1s = WGTADJ1S) %>% #SCHOOL WEIGHT ADJUSTMENT-STUDENT STUDY
mutate(wgtfac2s = WGTFAC2S) %>% #CLASS WEIGHT FACTOR
mutate(wgtadj2s = WGTADJ2S) %>% #CLASS WEIGHT ADJUSTMENT
mutate(wgtadj3s = WGTADJ3S) %>% #STUDENT WEIGHT ADJUSTMENT
mutate(jkzones = JKZONES) %>% #JACKKNIFE ZONE - STUDENT STUDY
mutate(jkreps = JKREPS) %>% #JACKKNIFE REPLICATE CODE
select(519:571)
#Merge data
dict <- rbind(dict09, dict16)
#All observations with complete row data
dict2 <- dict[complete.cases(dict),]
#Number observations
dict_count <- dict %>%
group_by(time, country) %>%
dplyr::summarise(N=n()) %>%
mutate(Prop. = N / sum(N)) %>%
arrange(country)
#Table
kable(dict_count, align = c("cccc"),
col.names = c("Year","Country", "Prop.", "N"),
caption = "Sample with all observations", format="html") %>%
kable_styling(bootstrap_options = c("striped", "hover"))| time | country | N | Prop. |
|---|---|---|---|
| 2009 | CHL | 5173 | 0.1730332 |
| 2016 | CHL | 5081 | 0.2006793 |
| 2009 | COL | 6200 | 0.2073856 |
| 2016 | COL | 5609 | 0.2215332 |
| 2009 | DOM | 4569 | 0.1528298 |
| 2016 | DOM | 3937 | 0.1554959 |
| 2009 | GTM | 3998 | 0.1337303 |
| 2009 | MEX | 6565 | 0.2195946 |
| 2016 | MEX | 5526 | 0.2182551 |
| 2016 | PER | 5166 | 0.2040365 |
| 2009 | PRY | 3391 | 0.1134265 |
#Number observations delete missing values
dict_count2 <- dict2 %>%
group_by(time, country) %>%
dplyr::summarise(N=n(), Prop. = (n()/nrow(dict2))) %>%
arrange(country)
#Table
kable(dict_count2, caption = "Sample without missing", format="html",
col.names = c("Year","Country", "Prop.", "N")) %>%
kable_styling(bootstrap_options = c("striped", "hover"))| time | country | N | Prop. |
|---|---|---|---|
| 2009 | CHL | 4511 | 0.1093337 |
| 2016 | CHL | 4070 | 0.0986451 |
| 2009 | COL | 4790 | 0.1160959 |
| 2016 | COL | 4461 | 0.1081219 |
| 2009 | DOM | 2164 | 0.0524492 |
| 2016 | DOM | 2359 | 0.0571754 |
| 2009 | GTM | 2930 | 0.0710148 |
| 2009 | MEX | 5127 | 0.1242638 |
| 2016 | MEX | 4530 | 0.1097942 |
| 2016 | PER | 4169 | 0.1010446 |
| 2009 | PRY | 2148 | 0.0520614 |
#Dictatorships are justified when they bring economic benefits 2016: LS2P03E - LS3G02E
bar_civic <- ggplot(subset(dict, !is.na(dict_benefits)), aes(as.factor(dict_benefits), group = country)) +
geom_bar(aes(y = ..prop.., group = country)) +
geom_text(aes(y= ..prop.. , label = scales::percent(..prop..)), stat= "count", vjust = -0.5) +
scale_y_continuous(labels = scales::percent, limits = c(0,1)) +
facet_grid(country ~ time) +
ggtitle("Dictatorship are justified when bring economic benefits") +
scale_x_discrete(labels = c("Very Disagree", "Disagree", "Agree", "Very Agree")) +
labs(x = "Agreement", y = "%")
bar_civic bar_civic <- ggplot(dict, aes(as.factor(dict_benefits), group = country)) +
geom_bar(aes(y = ..prop.., group = country), na.rm = TRUE) +
geom_text(aes(y= ..prop.. , label = scales::percent(..prop..)), stat= "count", vjust = -0.5) +
scale_y_continuous(labels = scales::percent, limits = c(0,1)) +
facet_grid(country ~ time) +
ggtitle("Dictatorship are justified when bring economic benefits (include missing)") +
scale_x_discrete(labels = c("Very Disagree", "Disagree", "Agree", "Very Agree")) +
labs(x = "Agreement", y = "%")
bar_civic #Dictatorships are justified when they bring order and safety 2009: LS2P03D - LS3G02D
bar_civic <- ggplot(subset(dict, !is.na(dict_safety)), aes(as.factor(dict_safety), group = country)) +
geom_bar(aes(y = ..prop.., group = country)) +
geom_text(aes(y= ..prop.. , label = scales::percent(..prop..)), stat= "count", vjust = -0.5) +
scale_y_continuous(labels = scales::percent, limits = c(0,1)) +
facet_grid(country ~ time) +
ggtitle("Dictatorship are justified when bring order and security") +
scale_x_discrete(labels = c("Very Disagree", "Disagree", "Agree", "Very Agree")) +
labs(x = "Agreement", y = "%")
bar_civic bar_civic <- ggplot(dict, aes(as.factor(dict_safety), group = country)) +
geom_bar(aes(y = ..prop.., group = country), na.rm = TRUE) +
geom_text(aes(y= ..prop.. , label = scales::percent(..prop..)), stat= "count", vjust = -0.5) +
scale_y_continuous(labels = scales::percent, limits = c(0,1)) +
facet_grid(country ~ time) +
ggtitle("Dictatorship are justified when bring order and security (include missing)") +
scale_x_discrete(labels = c("Very Disagree", "Disagree", "Agree", "Very Agree")) +
labs(x = "Agreement", y = "%")
bar_civic #Proxy Civic Knowledge
civic_country_mean09 <- dict %>% filter(time==2009) %>% group_by(country) %>%
dplyr::summarise(mean=mean(civic_knowledge),sd=sd(civic_knowledge),n=n()) %>%
dplyr::mutate(se=sd/sqrt(n)) %>%
mutate (time=2009)
civic_country_mean16 <- dict %>% filter(time==2016) %>% group_by(country) %>%
dplyr::summarise(mean=mean(civic_knowledge),sd=sd(civic_knowledge),n=n()) %>%
dplyr::mutate(se=sd/sqrt(n)) %>%
mutate (time=2016)
civic_country_mean <- merge(civic_country_mean09, civic_country_mean16, all = T)
kable(civic_country_mean, align = c("cccccc"), caption = "Mean Civic Knowledge") %>%
kable_styling(bootstrap_options = c("striped", "hover"))| country | mean | sd | n | se | time |
|---|---|---|---|---|---|
| CHL | 490.2998 | 91.60244 | 5081 | 1.2850867 | 2016 |
| CHL | 494.0536 | 85.69706 | 5173 | 1.1915017 | 2009 |
| COL | 465.8547 | 77.26525 | 6200 | 0.9812696 | 2009 |
| COL | 486.0054 | 79.18727 | 5609 | 1.0573351 | 2016 |
| DOM | 380.9117 | 61.77524 | 4569 | 0.9139109 | 2009 |
| DOM | 382.8483 | 75.71249 | 3937 | 1.2066598 | 2016 |
| GTM | 432.6359 | 71.50737 | 3998 | 1.1309136 | 2009 |
| MEX | 455.7181 | 78.47208 | 6565 | 0.9684959 | 2009 |
| MEX | 469.3019 | 79.25553 | 5526 | 1.0661643 | 2016 |
| PER | 442.6917 | 87.93071 | 5166 | 1.2233856 | 2016 |
| PRY | 428.7423 | 84.05566 | 3391 | 1.4434543 | 2009 |
#Graphs Bar
#All
civic_know <- ggplot(civic_country_mean, aes(reorder(to_label(country), -mean),mean), group = time)
civic_know <- civic_know + geom_bar(stat = "summary") +
facet_grid(~ time) +
geom_text(aes(label = format(mean, digits = 2), vjust=0.3, hjust=-0.2), size=2, colour="black") +
coord_flip() +
theme(axis.text=element_text(size=5,face="bold"),
axis.title=element_text(size=10,face="bold")) +
labs(x="Country", y="Civic Knowledge")
civic_know#Boxplot
box_civic = ggplot(dict, aes(reorder(to_label(country), -civic_knowledge), civic_knowledge), group = time)
box_civic + geom_boxplot() +
facet_grid(~ time) +
coord_flip() +
theme(axis.text=element_text(size=5),
axis.title=element_text(size=10,face="bold")) +
labs(x=" ", y="Civic Knowledge")#Dictatorships are justified when they bring economic benefits
scatter <- ggplot(dict, aes(civic_knowledge, dict_benefits, colour = factor(country)))
scatter + geom_smooth(method = "lm", alpha = 0.1) +
facet_wrap(~ time) +
labs(x = "Civic knowledge", y = "Support to dictatorship (economic benefits)", colour = "country") #Dictatorships are justified when they bring order and safety
scatter <- ggplot(dict, aes(civic_knowledge, dict_safety, colour = factor(country)))
scatter + geom_smooth(method = "lm", alpha = 0.1) +
facet_wrap(~ time) +
labs(x = "Civic knowledge", y = "Support to dictatorship (order and safety)", colour = "country") #Dictatorships are justified mean
scatter <- ggplot(dict, aes(civic_knowledge, dict, colour = factor(country)))
scatter + geom_smooth(method = "lm", alpha = 0.1) +
facet_wrap(~ time) +
labs(x = "Civic knowledge", y = "Support to dictatorship (mean)", colour = "country") #Trust in civic institutions and civic knowledge
scatter <- ggplot(dict, aes(civic_knowledge, s_intrust, colour = factor(country)))
scatter + geom_smooth(method = "lm", alpha = 0.1) +
facet_wrap(~ time) +
labs(x = "Civic knowledge", y = "Trust in civic institutions", colour = "country") in_trust09 <- dict2 %>% filter(time==2009) %>% group_by(country) %>%
dplyr::summarise(mean=mean(s_intrust),sd=sd(s_intrust),n=n()) %>%
dplyr::mutate(se=sd/sqrt(n)) %>%
mutate (time=2009)
in_trust16 <- dict2 %>% filter(time==2016) %>% group_by(country) %>%
dplyr::summarise(mean=mean(s_intrust),sd=sd(s_intrust),n=n()) %>%
dplyr::mutate(se=sd/sqrt(n)) %>%
mutate (time=2016)
in_trust_mean <- merge(in_trust09, in_trust16, all = T)
kable(in_trust_mean, align = c("cccccc"), caption = "Mean trust in civic institutions") %>%
kable_styling(bootstrap_options = c("striped", "hover"))| country | mean | sd | n | se | time |
|---|---|---|---|---|---|
| CHL | 47.06615 | 10.965115 | 4070 | 0.1718763 | 2016 |
| CHL | 49.81702 | 9.650716 | 4511 | 0.1436889 | 2009 |
| COL | 48.06496 | 9.497960 | 4461 | 0.1422048 | 2016 |
| COL | 49.35341 | 10.385844 | 4790 | 0.1500631 | 2009 |
| DOM | 54.14559 | 11.956145 | 2164 | 0.2570174 | 2009 |
| DOM | 54.98023 | 11.327530 | 2359 | 0.2332229 | 2016 |
| GTM | 46.91566 | 9.569341 | 2930 | 0.1767861 | 2009 |
| MEX | 48.46713 | 10.355470 | 5127 | 0.1446233 | 2009 |
| MEX | 49.61967 | 10.893892 | 4530 | 0.1618579 | 2016 |
| PER | 47.84578 | 9.585716 | 4169 | 0.1484597 | 2016 |
| PRY | 49.42522 | 9.333150 | 2148 | 0.2013776 | 2009 |
#Graphs Bar
#All
bar_intrust <- ggplot(in_trust_mean, aes(reorder(to_label(country), mean),mean), group = time)
bar_intrust <- bar_intrust + geom_bar(stat = "summary") +
facet_grid(~ time) +
geom_text(aes(label = format(mean, digits = 2), vjust=0.3, hjust=-0.2), size=2, colour="black") +
coord_flip() +
theme(axis.text=element_text(size=5,face="bold"),
axis.title=element_text(size=10,face="bold")) +
labs(x="Country", y="Trust in civic institutions")
bar_intrust#Boxplot
box_intrust = ggplot(dict, aes(reorder(to_label(country), -s_intrust), s_intrust), group = time)
box_intrust + geom_boxplot() +
facet_grid(~ time) +
coord_flip() +
theme(axis.text=element_text(size=5),
axis.title=element_text(size=10,face="bold")) +
labs(x=" ", y="Trust in civic institutions")#Dictatorships are justified when they bring economic benefits
scatter <- ggplot(dict, aes(s_intrust, dict_benefits, colour = factor(country)))
scatter + geom_smooth(method = "lm", alpha = 0.1) +
facet_wrap(~ time) +
labs(x = "Trust in civic institutions", y = "Support to dictatorship (economic benefits)", colour = "country") #Dictatorships are justified when they bring order and safety
scatter <- ggplot(dict, aes(s_intrust, dict_safety, colour = factor(country)))
scatter + geom_smooth(method = "lm", alpha = 0.1) +
facet_wrap(~ time) +
labs(x = "Trust in civic institutions", y = "Support to dictatorship (order and safety)", colour = "country") #Dictatorships are justified mean
scatter <- ggplot(dict, aes(s_intrust, dict, colour = factor(country)))
scatter + geom_smooth(method = "lm", alpha = 0.1) +
facet_wrap(~ time) +
labs(x = "Trust in civic institutions", y = "Support to dictatorship (mean)", colour = "country") #Models Chile
ch09= dict %>% filter(country=="CHL" & time==2009)
mch09 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=ch09)
ch16= dict %>% filter(country=="CHL" & time==2016)
mch16 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=ch16)
#Models Colombia
col09= dict %>% filter(country=="COL" & time==2009)
mcol09 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=col09)
col16= dict %>% filter(country=="COL" & time==2016)
mcol16 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=col16)
#Models República Dominicana
dom09= dict %>% filter(country=="DOM" & time==2009)
mdom09 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=dom09)
dom16= dict %>% filter(country=="DOM" & time==2016)
mdom16 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=dom16)
#Models México
mex09= dict %>% filter(country=="MEX" & time==2009)
mmex09 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=mex09)
mex16= dict %>% filter(country=="MEX" & time==2016)
mmex16 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=mex16)
#Models Guatemala 2009
gtm09= dict %>% filter(country=="GTM" & time==2009)
mgtm09 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=gtm09)
#Models Paraguay 2009
pry09= dict %>% filter(country=="PRY" & time==2009)
mpry09 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=pry09)
#Models Perú 2016
per16= dict %>% filter(country=="PER" & time==2016)
mper16 = lmer(dict ~ s_intrust + civic_knowledge + (1 | idschool), weights=totwgts, data=per16)
#Table
library(stargazer)
stargazer(l=list(mch09,mch16,mcol09,mcol16,mdom09, mdom16,mmex09, mmex16), digits = 3, type="html",
column.labels=c("Chile 2009", "Chile 2016", "Colombia 2009", "Colombia 2016", "Rep. Dom. 2009", "Rep. Dom. 2016", "Mexico 2009", "Mexico 2016"),
covariate.labels =c("Trust institutions", "Civic Knowledge"),
dep.var.labels = "Support dictatorship")| Dependent variable: | ||||||||
| Support dictatorship | ||||||||
| Chile 2009 | Chile 2016 | Colombia 2009 | Colombia 2016 | Rep. Dom. 2009 | Rep. Dom. 2016 | Mexico 2009 | Mexico 2016 | |
| (1) | (2) | (3) | (4) | (5) | (6) | (7) | (8) | |
| Trust institutions | 0.014*** | 0.013*** | 0.009*** | 0.011*** | 0.011*** | 0.012*** | 0.010*** | 0.016*** |
| (0.001) | (0.001) | (0.001) | (0.001) | (0.001) | (0.001) | (0.001) | (0.001) | |
| Civic Knowledge | -0.003*** | -0.002*** | -0.002*** | -0.002*** | -0.002*** | -0.003*** | -0.002*** | -0.002*** |
| (0.0001) | (0.0002) | (0.0001) | (0.0001) | (0.0002) | (0.0002) | (0.0001) | (0.0001) | |
| Constant | 3.330*** | 3.059*** | 3.231*** | 3.179*** | 3.228*** | 3.626*** | 3.184*** | 2.819*** |
| (0.094) | (0.095) | (0.078) | (0.088) | (0.124) | (0.118) | (0.080) | (0.091) | |
| Observations | 5,059 | 4,909 | 5,733 | 5,325 | 3,450 | 3,395 | 6,129 | 5,289 |
| Log Likelihood | -5,915.167 | -6,382.484 | -5,899.622 | -5,766.078 | -4,168.101 | -4,122.095 | -6,661.336 | -6,419.753 |
| Akaike Inf. Crit. | 11,840.330 | 12,774.970 | 11,809.240 | 11,542.160 | 8,346.201 | 8,254.190 | 13,332.670 | 12,849.510 |
| Bayesian Inf. Crit. | 11,872.980 | 12,807.460 | 11,842.510 | 11,575.060 | 8,376.932 | 8,284.840 | 13,366.270 | 12,882.370 |
| Note: | p<0.1; p<0.05; p<0.01 | |||||||
stargazer(l=list(mgtm09, mpry09, mper16), digits = 3, type="html",
column.labels=c("Guatemala 2009", "Paraguay 2016", "Perú 2009"),
covariate.labels =c("Trust institutions", "Civic Knowledge"),
dep.var.labels = "Support dictatorship")| Dependent variable: | |||
| Support dictatorship | |||
| Guatemala 2009 | Paraguay 2016 | Perú 2009 | |
| (1) | (2) | (3) | |
| Trust institutions | 0.009*** | 0.008*** | 0.010*** |
| (0.001) | (0.001) | (0.001) | |
| Civic Knowledge | -0.002*** | -0.003*** | -0.001*** |
| (0.0002) | (0.0002) | (0.0001) | |
| Constant | 3.320*** | 3.486*** | 2.814*** |
| (0.100) | (0.120) | (0.082) | |
| Observations | 3,745 | 2,880 | 4,975 |
| Log Likelihood | -3,779.178 | -3,237.766 | -4,917.179 |
| Akaike Inf. Crit. | 7,568.355 | 6,485.532 | 9,844.359 |
| Bayesian Inf. Crit. | 7,599.496 | 6,515.360 | 9,876.919 |
| Note: | p<0.1; p<0.05; p<0.01 | ||
$CHL
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 2.000 3.000 2.534 3.000 4.000 106
$COL
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.00 2.00 3.00 2.78 3.00 4.00 250
$DOM
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 2.000 3.000 2.875 4.000 4.000 598
$GTM
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 2.000 3.000 2.932 3.000 4.000 84
$MEX
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 2.000 3.000 2.755 3.000 4.000 270
$PER
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 2.000 3.000 2.859 3.000 4.000 65
$PRY
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 2.000 3.000 2.731 3.000 4.000 150
$CHL
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 2.000 3.000 2.557 3.000 4.000 124
$COL
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.00 2.00 3.00 2.83 3.00 4.00 288
$DOM
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 2.000 3.000 2.935 4.000 4.000 622
$GTM
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 3.000 3.000 2.943 3.000 4.000 98
$MEX
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 2.000 3.000 2.753 3.000 4.000 306
$PER
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 3.000 3.000 2.924 3.000 4.000 78
$PRY
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
1.000 2.000 3.000 2.804 3.000 4.000 138
$CHL
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
20.21 43.02 47.28 48.48 54.39 77.35 165
$COL
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
20.21 43.02 47.28 48.89 54.39 77.35 547
$DOM
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
20.21 47.27 54.36 54.59 62.22 77.35 1346
$GTM
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
20.21 40.94 45.12 47.17 51.90 77.35 194
$MEX
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
20.21 40.98 47.28 49.16 54.39 77.35 457
$PER
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
21.78 40.98 47.28 48.03 54.36 75.73 129
$PRY
Min. 1st Qu. Median Mean 3rd Qu. Max. NA's
20.21 43.02 49.53 49.66 54.39 77.35 423
$CHL
Min. 1st Qu. Median Mean 3rd Qu. Max.
206.6 426.8 494.8 492.2 559.4 780.4
$COL
Min. 1st Qu. Median Mean 3rd Qu. Max.
194.1 419.5 478.4 475.4 531.6 707.2
$DOM
Min. 1st Qu. Median Mean 3rd Qu. Max.
141.0 334.5 376.8 381.8 425.6 629.2
$GTM
Min. 1st Qu. Median Mean 3rd Qu. Max.
183.3 385.0 429.8 432.6 482.2 659.0
$MEX
Min. 1st Qu. Median Mean 3rd Qu. Max.
175.1 403.3 463.3 461.9 520.2 715.2
$PER
Min. 1st Qu. Median Mean 3rd Qu. Max.
174.7 378.4 444.7 442.7 508.6 664.6
$PRY
Min. 1st Qu. Median Mean 3rd Qu. Max.
156.8 369.8 423.7 428.7 488.1 711.0
#Model to 2009
model09 = lmer(dict ~ 1 + s_intrust + civic_knowledge + (1 | country), weights=totwgts, data=dict09)
stargazer(model09, digits = 3, type="html",
covariate.labels =c("Trust institutions", "Civic Knowledge"),
dep.var.labels = "Support dictatorship")| Dependent variable: | |
| Support dictatorship | |
| Trust institutions | 0.010*** |
| (0.0004) | |
| Civic Knowledge | -0.002*** |
| (0.0001) | |
| Constant | 3.197*** |
| (0.053) | |
| Observations | 26,996 |
| Log Likelihood | -35,291.470 |
| Akaike Inf. Crit. | 70,592.940 |
| Bayesian Inf. Crit. | 70,633.950 |
| Note: | p<0.1; p<0.05; p<0.01 |
library(sjPlot)
fig09=plot_model(model09, type = "re",
show.legend = FALSE,
show.values = TRUE,
facet.grid = FALSE,
y.offset = .4,
value.offset = .4,
value.size = 3.5,
color="darkgray",
sort.est= 2,
title = " ",)
fig09#Model to 2016
model16 = lmer(dict ~ 1 + s_intrust + civic_knowledge + (1 | country), weights=totwgts, data=dict16)
stargazer(model16, digits = 3, type="html",
covariate.labels =c("Trust institutions", "Civic Knowledge"),
dep.var.labels = "Support dictatorship")| Dependent variable: | |
| Support dictatorship | |
| Trust institutions | 0.015*** |
| (0.0005) | |
| Civic Knowledge | -0.002*** |
| (0.0001) | |
| Constant | 2.924*** |
| (0.069) | |
| Observations | 23,893 |
| Log Likelihood | -32,236.060 |
| Akaike Inf. Crit. | 64,482.110 |
| Bayesian Inf. Crit. | 64,522.520 |
| Note: | p<0.1; p<0.05; p<0.01 |
fig16=plot_model(model16, type = "re",
show.legend = FALSE,
show.values = TRUE,
facet.grid = FALSE,
y.offset = .4,
value.offset = .4,
value.size = 3.5,
color="darkgray",
sort.est= 2,
title = " ",)
fig16